Escrita e Conteúdo

Technical documentation writing skill covering API docs, architecture documentation, deployment guides, and various technical writing best practices. Use this skill when creating technical documentation, writing API documentation, creating architecture design documents, or need templates for deployment and operations manuals.

Avoid mutable variables like IORef, STRef, and ST in Haskell and prefer immutable records. Use STM variables such as TVar for thread communication. Use when writing or reviewing Haskell code that uses mutable state or concurrency.

Generate images with xAI's Grok image models (grok-2-image / grok-2-image-1212). Use when the user asks for Grok-generated images, mentions xAI image generation, or wants an OpenAI-compatible image API alternative. Generation only — Grok image models do not support edit, mask, or reference-image inputs.

Forbid unsafe Haskell functions such as unsafePerformIO, unsafeCoerce, and other unsafe-prefixed functions. Use when writing or reviewing Haskell code that uses any unsafe-prefixed function.

Habilidade de autenticação de voz de escrita e eliminação de 'cheiro de IA'. Ativa quando o usuário deseja que a escrita gerada por IA soe especificamente como ele, analisando uma amostra para replicar seu estilo único.

Do not discard a function's final value with return (), pure (), or void; adjust the type to return the value and let the caller discard it when unneeded. Use when writing or reviewing Haskell functions that return unit or discard results.

Prefer undefined over null in TypeScript/JavaScript. Use == null for nullish checks. Use when writing or reviewing code that handles absent values.

Core markdown syntax skill for Obsidian. Enforces strict parsing and authoring of Obsidian proprietary syntax (Wikilinks, Blocks, Headings, Aliases, Embeds, Callouts). Use when reading, writing, or validating Obsidian-flavored markdown.

Load existing code-to-docs vault context into the conversation before coding. Read-only — never writes files. Provides architecture overview, module summaries, known issues, and session history. Use when starting a coding session, loading doc context, or catching up on a documented codebase.

Padrões de lista e tupla para bioinformática — divisão de códons, registros de coordenadas genéticas, tuplas nomeadas, ordenação por GC/comprimento e armadilhas de cópia.

Construção, pontuação, varredura, conteúdo de informação, logos de sequência de PWM/PFM/PPM e conversão de padrões PROSITE.

Explora o uso de listas e tuplas em bioinformática para extração de códons, registros de coordenadas genômicas, tuplas nomeadas e semântica de cópia, focando apenas em padrões bioespecíficos.